Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Code Review by Severity

    1

    Reviews your diff for bugs, security issues and debt, and returns a findings table ranked by severity.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Code Review by Severity

    Code Review by Severity

    Example session with this skill installed

    /review

    • Read your context and instructions
    • Compiled the code review by

    I reviewed the two staged files (src/auth/service.ts and src/middleware/auth.ts). There are three serious problems, one of them an authentication bypass.

    Sev.File:lineProblemSuggestion
    🔴 highsrc/middleware/auth.ts:8-9Auth bypass. verifyToken now returns null for an invalid or expired token. The middleware still sets req.user = null and calls next(). A request with Authorization: Bearer garbage therefore passes requireAuth. Any handler that only checks the middleware, or reads req.user?.sub loosely, is exposed.After verifying, add if (!payload) return res.status(401).json({ error: "invalid token" }); before next().
    🔴 highsrc/auth/service.ts:21SQL injection. findUserByEmail interpolates email straight into the query. An input like ' OR '1'='1 returns arbitrary users, and '; DROP TABLE users;-- can run further statements, depending on the driver.Use a parameterized query, e.g. db.query("SELECT * FROM users WHERE email = $1", [email]), with the placeholder syntax your driver uses. Replace db: any with a real type, and select only the columns you need instead of *.
    🔴 highsrc/auth/service.ts:4Secret in logs. console.log("auth init", config.JWT_SECRET) writes the JWT signing secret to stdout on every start. Anyone with log access can forge valid tokens.Delete the line. If you need a startup message, log without the secret.
    🟡 mediumsrc/auth/service.ts:13-17catch {} swallows every error and returns null. A bad token, an expired token and a misconfigured secret all look the same, which makes failures hard to diagnose. jwt.verify can also return a string payload, so callers can't rely on .sub.Return a typed result, such as { sub: string } | null, or narrow the payload type. Log or distinguish TokenExpiredError from other errors.
    🟡 mediumsrc/middleware/auth.ts:6replace("Bearer ", "") doesn't check the scheme. A header of Basic xyz becomes Basic xyz and is passed to verify. That is harmless once the bypass is fixed, but sloppy.Match with /^Bearer (.+)$/ and return 401 if it doesn't match.
    ⚪ minorsrc/middleware/auth.ts:4Dropping async is correct now that verifyToken is synchronous.None. This is fine as is.
    ⚪ minorsrc/auth/service.tsThere are no tests for verifyToken or findUserByEmail. A test for "invalid token returns 401" would have caught the bypass.Add tests for valid, expired, malformed and missing tokens.

    I recommend not merging until the three 🔴 items are fixed. I haven't changed anything. Tell me if you want me to apply the fixes.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Type "review" and Claude reads the diff plus the context of every touched file, then checks in a fixed order:

    1. Correctness: edge cases, null/undefined, missing await, race conditions, off-by-one, swallowed errors.
    2. Security: injection (SQL, shell, XSS), secrets in code, input validation, missing authorization, sensitive data in logs.
    3. Data and API: irreversible migrations, breaking REST/GraphQL changes, N+1 queries.
    4. Performance: unnecessary React renders, wrong effect dependencies, queries in loops.
    5. Maintainability: duplication, confusing names, dead code, missing tests.

    Output: a table with severity (high / medium / minor), file:line, problem and suggestion. It only reports what it can justify with a concrete scenario, says so when it finds nothing serious, and never edits code unless you ask.

    Unofficial. Not affiliated with Anthropic.

    Does not automatically apply code changes. Requires git access to retrieve diffs. Focuses on logic and security rather than stylistic linting. Findings are suggestions from the model: always verify them before acting.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    **

    Read-only. Runs only git diff / git status and reads the changed files for context. It never writes files, runs project code or uses the network, and only edits code if you explicitly ask.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Any agent that supports the SKILL.md standard and can run git and read files, e.g. Claude Code, Codex CLI, Cursor. It was tested in Claude Code 2.1.

    It reads the actual diff plus the surrounding code of every touched file, and checks the same five areas every time (correctness, security, data/API, performance, maintainability), returning a findings table ranked by severity instead of free-form comments.

    It works on any language git can diff. The checklist includes specific checks for JavaScript/TypeScript, React (renders, effect dependencies), Node APIs and GraphQL (N+1, breaking schema changes).

    No. It only reads and reports. It edits code only if you explicitly ask it to apply a fix.

    A zip with one SKILL.md file. Install it by copying the "review" folder into .claude/skills/ in your project (or ~/.claude/skills/ for all projects). One-time payment, future updates included.

    New in Code Quality & Review